Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 120 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.5674. Min Act: -0.1700
Data Index: 6574598 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.5674. Min Act: -0.1700
Data Index: 763578 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.5362. Min Act: -0.1700
Data Index: 1582467 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.5049. Min Act: -0.1700
Data Index: 2014392 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.4424. Min Act: -0.1700
Data Index: 540147 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.3799. Min Act: -0.1700
Data Index: 8323534 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.3799. Min Act: -0.1700
Data Index: 5599784 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.3487. Min Act: -0.1700
Data Index: 4911932 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.3487. Min Act: -0.1700
Data Index: 5489067 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.3487. Min Act: -0.1700
Data Index: 438447 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.3174. Min Act: -0.1700
Data Index: 990801 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.3174. Min Act: -0.1700
Data Index: 7852120 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.2862. Min Act: -0.1700
Data Index: 7746963 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.2862. Min Act: -0.1700
Data Index: 5655468 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.2862. Min Act: -0.1700
Data Index: 1642822 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.2862. Min Act: -0.1700
Data Index: 793900 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.2862. Min Act: -0.1700
Data Index: 2703081 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.2862. Min Act: -0.1700
Data Index: 7256371 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.2549. Min Act: -0.1700
Data Index: 544440 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5674. Min Range: -6.5674
Max Act: 6.2549. Min Act: -0.1700
Data Index: 4583597 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19